The increasingly complex and interconnected train control information network is vulnerable to a variety of malicious traffic attacks,and the existing malicious traffic detection methods mainly rely on machine learnin...The increasingly complex and interconnected train control information network is vulnerable to a variety of malicious traffic attacks,and the existing malicious traffic detection methods mainly rely on machine learning,such as poor robustness,weak generalization,and a lack of ability to learn common features.Therefore,this paper proposes a malicious traffic identification method based on stacked sparse denoising autoencoders combined with a regularized extreme learning machine through particle swarm optimization.Firstly,the simulation environment of the Chinese train control system-3,was constructed for data acquisition.Then Pearson coefficient and other methods are used for pre-processing,then a stacked sparse denoising autoencoder is used to achieve nonlinear dimensionality reduction of features,and finally regularization extreme learning machine optimized by particle swarm optimization is used to achieve classification.Experimental data show that the proposed method has good training performance,with an average accuracy of 97.57%and a false negative rate of 2.43%,which is better than other alternative methods.In addition,ablation experiments were performed to evaluate the contribution of each component,and the results showed that the combination of methods was superior to individual methods.To further evaluate the generalization ability of the model in different scenarios,publicly available data sets of industrial control system networks were used.The results show that the model has robust detection capability in various types of network attacks.展开更多
To achieve carbon neutrality,the Chinese government needs to gain a comprehensive understanding of the sources and drivers of greenhouse gas(GHG)emissions,particularly at the county level.Anji County in eastern China ...To achieve carbon neutrality,the Chinese government needs to gain a comprehensive understanding of the sources and drivers of greenhouse gas(GHG)emissions,particularly at the county level.Anji County in eastern China is a typical example of an industrial transformation from quarrying to a low-carbon economy.This study analyzed the decoupling types and structural characteristics of GHG emissions and the driving factors of carbon dioxide(CO_(2))emissions in the Anji from 2006 to 2019,and explored the differences between countylevel and provincial-level or city-level results.It was observed that energy-related activities are the main source of GHG emissions in Anji and that economic development is the driving factor behind the increasing CO_(2)emissions.However,industrial transformation and upgradation coupled with the alternative use of clean energy limit the growth of GHG emissions.This study details the GHG emissions of county during the industrial transformation stage and provides corresponding policy recommendations for county governments.展开更多
文摘The increasingly complex and interconnected train control information network is vulnerable to a variety of malicious traffic attacks,and the existing malicious traffic detection methods mainly rely on machine learning,such as poor robustness,weak generalization,and a lack of ability to learn common features.Therefore,this paper proposes a malicious traffic identification method based on stacked sparse denoising autoencoders combined with a regularized extreme learning machine through particle swarm optimization.Firstly,the simulation environment of the Chinese train control system-3,was constructed for data acquisition.Then Pearson coefficient and other methods are used for pre-processing,then a stacked sparse denoising autoencoder is used to achieve nonlinear dimensionality reduction of features,and finally regularization extreme learning machine optimized by particle swarm optimization is used to achieve classification.Experimental data show that the proposed method has good training performance,with an average accuracy of 97.57%and a false negative rate of 2.43%,which is better than other alternative methods.In addition,ablation experiments were performed to evaluate the contribution of each component,and the results showed that the combination of methods was superior to individual methods.To further evaluate the generalization ability of the model in different scenarios,publicly available data sets of industrial control system networks were used.The results show that the model has robust detection capability in various types of network attacks.
基金supported by the National Natural Science Foundation of China(Nos.22278168 and 22276064)the MOE Key Laboratory of Resources and Environmental System Optimization(No.KLRE-KF202205)the Science and Technology Project of Fujian province(No.2022Y3007)。
文摘To achieve carbon neutrality,the Chinese government needs to gain a comprehensive understanding of the sources and drivers of greenhouse gas(GHG)emissions,particularly at the county level.Anji County in eastern China is a typical example of an industrial transformation from quarrying to a low-carbon economy.This study analyzed the decoupling types and structural characteristics of GHG emissions and the driving factors of carbon dioxide(CO_(2))emissions in the Anji from 2006 to 2019,and explored the differences between countylevel and provincial-level or city-level results.It was observed that energy-related activities are the main source of GHG emissions in Anji and that economic development is the driving factor behind the increasing CO_(2)emissions.However,industrial transformation and upgradation coupled with the alternative use of clean energy limit the growth of GHG emissions.This study details the GHG emissions of county during the industrial transformation stage and provides corresponding policy recommendations for county governments.
